PulseAugur
实时 12:46:02

New framework aids authors in generating AI-assisted peer review responses

Researchers have developed a new framework called REspGen to assist authors in generating responses to peer reviews, integrating author expertise and intent. This framework is accompanied by Re3Align, a large dataset of review-response-revision triplets, and REspEval, a comprehensive suite of over 20 metrics for evaluating response quality. Experiments using state-of-the-art large language models demonstrate the effectiveness of author input and evaluation-guided refinement in improving response generation. AI

影响 Introduces new tools and datasets for improving AI-assisted scientific communication and peer review processes.

排序理由 The cluster contains two academic papers discussing novel datasets, frameworks, and evaluation methods for AI-assisted response generation in scientific peer review.

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.CL TIER_1 English(EN) · Qian Ruan, Iryna Gurevych ·

    Author-in-the-Loop Response Generation and Evaluation: Integrating Author Expertise and Intent in Responses to Peer Review

    arXiv:2602.11173v3 Announce Type: replace Abstract: Author response (rebuttal) writing is a critical stage of scientific peer review that demands substantial author effort. In practice, authors possess domain expertise, author-only information, and response strategies - concrete …

  2. arXiv cs.LG TIER_1 English(EN) · Buxin Su, Jiayao Zhang, Natalie Collina, Yuling Yan, Didong Li, Kyunghyun Cho, Jianqing Fan, Aaron Roth, Weijie Su ·

    Rejoinder: The ICML 2023 Ranking Experiment: Examining Author Self-Assessment in ML/AI Peer Review

    arXiv:2605.25172v1 Announce Type: cross Abstract: This article is the rejoinder to ``The ICML 2023 Ranking Experiment: Examining Author Self-Assessment in ML/AI Peer Review,'' to appear in the Journal of the American Statistical Association with discussion. To address the practic…